SKILLEMALL.ai

BF computer-task-execution

Execute real user tasks across websites and local applications with a reliability-first strategy. Use when the user wants the agent to actually do something, not just answer: operate a website, complete a flow in a desktop app, send a message, edit content in a GUI, retrieve information from an app, or finish a multi-step computer task. Especially use when deciding between browser execution, app scripting, local UI automation, or low-intrusion execution paths.

ClawHub Agent Skills author: gift-is-coding v1.0.0 MIT-0 12 files body ≈ 2 394 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process F 57/100 · Will not run — References files that are not bundled: references/site-patterns/<domain>.md, references/site-patterns/<app-name>.md, references/site-patterns/<target>.md

GeneratorAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
66
Run on models
none yet
Process rating
F
57/100
Will not run
References files that are not bundled: references/site-patterns/<domain>.md, references/site-patterns/<app-name>.md, references/site-patterns/<target>.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Execute real user tasks across websites and local applications wit… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning missing-ref reference to a missing file: references/site-patterns/<domain>.md
  • warning missing-ref reference to a missing file: references/site-patterns/<app-name>.md
  • warning missing-ref reference to a missing file: references/site-patterns/<target>.md

Process rating: all ten parameters 57/100

Will not run. References files that are not bundled: references/site-patterns/<domain>.md, references/site-patterns/<app-name>.md, references/site-patterns/<target>.md
  • 0Tools and files. 3 referenced file(s) missing: references/site-patterns/<domain>.md, references/site-patterns/<app-name>.md, references/site-patterns/<target>.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Result and completion. Does not say what the result is
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 128 steps
  • 100Failures and branches. 12 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2394 tokens
  • 100Running it twice. Mutating operations check current state
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 464: enough signal without eating the budget
  • +4Structure: 31 headings
  • +3Step-by-step instructions: 128 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This instruction-only skill is coherent, but it is broad and includes a WeChat test pattern that could cause an agent to send a real message without clear user confirmation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026